Advertisement

A Rule Induction Model Empowered by Fuzzy-Rough Particle Swarm Optimization Algorithm for Classification of Microarray Dataset

Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 33)

Abstract

Selection of small number of genes from thousands of genes which may be responsible for causing cancer is still a challenging problem. Various computational intelligence methods have been used to deal with this issue. This study introduces a novel hybrid technique based on Fuzzy-Rough Particle Swarm Optimization (FRPSO) to identify a minimal subset of genes from thousands of candidate genes. Efficiency of the proposed method is tested with a rule based classifier MODLEM using three benchmark gene expression cancer datasets. This study reveals that the hybrid evolutionary Fuzzy-Rough induction rule model can identify the hidden relationship between the genes responsible for causing the disease. It also provides a rule set for diagnosis and prognosis of cancer datasets which helps to design drugs for the disease. Finally the function of identified genes are analyzed and validated from gene ontology website, DAVID, which shows the relationship of genes with the disease.

Keywords

Particle swarm optimization Population based algorithm Induction rule Rough-set Fuzzy-rough Minimal reduction 

References

  1. 1.
    Golub, T.R., Slonim, D.K., Tamayo, P., Huard, C., Gaasenbeek, M., Mesirov, J.P., Coller, H., Loh, M.L., Downing, J.R., Caligiuri, M.A., Bloomfield, C.D., Lander, E.S.: Molecular classification of cancer. Class discovery and class prediction by gene expression monitoring. Science 286(5439), 531–537 (1999)Google Scholar
  2. 2.
    Dash, M., Liu, H.: Feature selection for classification. Intell. Data Anal. 1(3), 131–156 (1997)CrossRefGoogle Scholar
  3. 3.
    Ahmad, A., Dey L.: A feature selection technique for classificatory analysis. Pattern Recognit. Lett. 26, 43–56 (2005)Google Scholar
  4. 4.
    Su, Y., Murali, T.M.: RankGene: identification of diagnostic genes based on expression data. Bioinformatics 19, 1578–1579 (2003)CrossRefGoogle Scholar
  5. 5.
    Ding, C., Peng, H.: Minimum redundancy feature selection from microarray gene expression data. J. Bioinf. Comput. Biol. 3(2), 185–205 (2005)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Maji, P.: f-information measures for efficient selection of discriminative genes from microarray data. IEEE Trans. Biomed. Eng. 56(4) 1063–1069 (2009)Google Scholar
  7. 7.
    Zadeh, L.A.: Fuzzy sets. Inf. Control 8, 338–353 (1965)CrossRefMathSciNetMATHGoogle Scholar
  8. 8.
    Pawlak, Z.: Rough Sets. Theoretical Aspects of Reasoning About Data. Kluwer, Norwell (1991)Google Scholar
  9. 9.
    Alba, E.: Gene selection in cancer classification using PSO/SVM and GA/SVM hybrid algorithms. IEEE C Evol. Comput. 9, 284–290 (2007)Google Scholar
  10. 10.
    Kennedy, J., Eberhart, R.: Particle swarm optimization. In: IEEE International Conference on Neural Networks—Conference Proceedings, vol. 4, pp. 1942–1948 (1995)Google Scholar
  11. 11.
    Chen, LF.: Particle swarm optimization for feature selection with application in obstructive sleep apnea diagnosis. Neural Comput. Appl. 21(8), 2087–2096 (2011)Google Scholar
  12. 12.
    Mohamad, M.S., et al.: Particle swarm optimization for gene selection in classifying cancer classes. In: Proceedings of the 14th International Symposium on Artificial Life and Robotics, pp. 762–765 (2009)Google Scholar
  13. 13.
    Stefanowski, J.: Changing representation of learning examples while inducing classifiers based on decision rules. In: Symposium on Artificial Intelligence Methods, 5–7 Nov 2003Google Scholar
  14. 14.
    Stefanowski, J.: Algorithms of rule induction for knowledge discovery. (In Polish), Habilitation Thesis published as Series Rozprawy no. 361. Poznan University of Technology Press, Poznan (2001)Google Scholar
  15. 15.
    Bioinformatics Laboratory, University of Ljubljana. http://www.biolab.si/supp/bi-ancer/projections/info/lungGSE1987.htm (1987)
  16. 16.
    Dudoit, S., Fridlyand, J.: Speed TP. Comparison of discrimination methods for the classification of tumors using gene expression data. J. Am. Stat. Assoc. 97, 77–86 (2002)Google Scholar
  17. 17.
    Jiang, P., et al.: MiPred. Classification of real and pseudo microRNA precursors using random forest prediction model with combined features. Nucleic Acids Res. 35, 339–344 (2007)CrossRefGoogle Scholar
  18. 18.
    Wang, Y., et al.: Predicting human microRNA precursors based on an optimized feature subset generated by GA-SVM. Genomics 98, 73–78 (2011)CrossRefGoogle Scholar
  19. 19.
    Nanni, L., Brahnam, S., Lumini, A.: Combining multiple approaches for gene [8] R. Kohavi, D. Sommerfield, feature subset selection using the wrapper method: overfitting and dynamic search space topology. In: Proceedings of the First International Conference on Knowledge Discovery and Data Mining, pp. 192–197. AAAI Press, Montreal (1995)Google Scholar
  20. 20.
    Kohavi, R., George, H., John.: Wrappers for feature subset selection. AIJ special issue on relevance. http://robotics.stanford.edu/~fronnyk,gjohng (1996)
  21. 21.
    Mohamad, M.S., et al.: Particle swarm optimization for gene selection in classifying cancer classes. In: Proceedings of the 14th International Symposium on Artificial Life and Robotics, pp. 762–765 (2009)Google Scholar
  22. 22.
    Zhao, W., et al.: A novel framework for gene selection. Int. J. Adv. Comput. Technol. 3, 184–191 (2011)Google Scholar
  23. 23.
    Chen, L.F., et al.: Particle swarm optimization for feature selection with application in obstructive sleep apnea diagnosis. Neural Comput. Appl. 21, 2087–2096 (2011)CrossRefGoogle Scholar
  24. 24.
    Chen, et al.: Gene selection for cancer identification: a decision tree model empowered by particle swarm optimization algorithm BMC Bioinf. 15(49) (2014). doi: 10.1186/1471-2105-15-49
  25. 25.
    Stefanowski, J.: The rough set based rule induction technique for classification problems. In: Proceedings of 6th European Conference on Intelligent Techniques and Soft Computing EUFIT’98, pp. 109–113. Aaachen (1998)Google Scholar
  26. 26.
    Grzymala-Busse, J.W.: Managing uncertainty in machine learning from examples. In: Proceedings of 3rd International Symposium in Intelligent Systems, pp. 70–84. IPI PAN Press, Wigry, Poland (1994) Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  1. 1.North Orissa UniversityBaripadaIndia

Personalised recommendations